Capture Career Notes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: the call invokes the configured LLM provider (cost/latency/external-dependency implication), a model matches or proposes an entity, output lands as drafts needing user approval, and text is stored verbatim as user-owned unverified content. These facts meaningfully extend the readOnly/openWorld/idempotent hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core action, each adding a distinct fact (matching/LLM, drafts+approval, verbatim storage). No filler or repetition of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-param, no-output-schema write tool the description covers purpose, behavior, side effects, and the approval gate well. The main residual gap is what the call returns (e.g. created draft point/entity identifiers), which the absence of an output schema leaves undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the load, and it does explain both parameters: 'text' is the user's own words stored verbatim, and 'entity_id' forces placement into a specific entity instead of model-matched. It stops short of telling the agent where entity_id values come from (e.g. kb_list_entities).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Capture free-text career news into DRAFT points') and immediately frames the pipeline role (draft → approval at /career). It is distinguishable from sibling kb_* tools like kb_create_entity, kb_edit_point, and kb_approve_points because it is the ingestion step, not the editing or approval step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for use (capture free-text career news; pass entity_id to force placement) and describes the downstream approval workflow. It does not, however, compare itself to alternatives such as kb_create_entity or kb_ingest_resume, so the agent gets context but no explicit when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.